accent-classifier / config.json
ylacombe's picture
Upload Wav2Vec2ForSequenceClassification
12b4639 verified
{
"_name_or_path": "/fsx/yoach/accent_classification_output_final_v3_smaller_dataset/",
"activation_dropout": 0.0,
"adapter_attn_dim": 16,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": false,
"apply_spec_augment": true,
"architectures": [
"Wav2Vec2ForSequenceClassification"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"classifier_proj_size": 1024,
"codevector_dim": 1024,
"contrastive_logits_temperature": 0.1,
"conv_bias": true,
"conv_dim": [
512,
512,
512,
512,
512,
512,
512
],
"conv_kernel": [
10,
3,
3,
3,
3,
2,
2
],
"conv_stride": [
5,
2,
2,
2,
2,
2,
2
],
"ctc_loss_reduction": "mean",
"ctc_zero_infinity": false,
"diversity_loss_weight": 0.1,
"do_stable_layer_norm": true,
"eos_token_id": 2,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.0,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.0,
"finetuning_task": "audio-classification",
"hidden_act": "gelu",
"hidden_dropout": 0.0,
"hidden_size": 1280,
"id2label": {
"0": "American",
"1": "Australian",
"2": "Canadian",
"3": "Chinese",
"4": "Czech",
"5": "Dutch",
"6": "Eastern european",
"7": "English",
"8": "Estonian",
"9": "Finnish",
"10": "French",
"11": "German",
"12": "Hungarian",
"13": "Indian",
"14": "Irish",
"15": "Italian",
"16": "Jamaican",
"17": "Latin american",
"18": "Malaysian",
"19": "New zealand",
"20": "Polish",
"21": "Romanian",
"22": "Scottish",
"23": "Singaporean",
"24": "Slovak",
"25": "South african",
"26": "Spanish",
"27": "Welsh"
},
"initializer_range": 0.02,
"intermediate_size": 5120,
"label2id": {
"American": "0",
"Australian": "1",
"Canadian": "2",
"Chinese": "3",
"Czech": "4",
"Dutch": "5",
"Eastern european": "6",
"English": "7",
"Estonian": "8",
"Finnish": "9",
"French": "10",
"German": "11",
"Hungarian": "12",
"Indian": "13",
"Irish": "14",
"Italian": "15",
"Jamaican": "16",
"Latin american": "17",
"Malaysian": "18",
"New zealand": "19",
"Polish": "20",
"Romanian": "21",
"Scottish": "22",
"Singaporean": "23",
"Slovak": "24",
"South african": "25",
"Spanish": "26",
"Welsh": "27"
},
"layer_norm_eps": 1e-05,
"layerdrop": 0.0,
"mask_feature_length": 10,
"mask_feature_min_masks": 0,
"mask_feature_prob": 0.0,
"mask_time_length": 10,
"mask_time_min_masks": 2,
"mask_time_prob": 0.05,
"model_type": "wav2vec2",
"num_adapter_layers": 3,
"num_attention_heads": 16,
"num_codevector_groups": 2,
"num_codevectors_per_group": 320,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 48,
"num_negatives": 100,
"output_hidden_size": 1280,
"pad_token_id": 0,
"proj_codevector_dim": 1024,
"tdnn_dilation": [
1,
2,
3,
1,
1
],
"tdnn_dim": [
512,
512,
512,
512,
1500
],
"tdnn_kernel": [
5,
3,
3,
1,
1
],
"torch_dtype": "float32",
"transformers_version": "4.40.2",
"use_weighted_layer_sum": false,
"vocab_size": 154,
"xvector_output_dim": 512
}